Sensible scenes

visual understanding of complex structures through causal analysis

Matthew Brand*, Lawrence A Birnbaum, Paul Cooper

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

An important result of visual understanding is an explanation of a scene's causal structure: How action - usually motion - is originated, constrained, and prevented, and how this determines what will happen in the immediate future. To be useful for a purposeful agent, these explanations must also capture the scene in terms of the functional properties of its objects - their purposes, uses, and affordances for manipulation. Design knowledge describes how the world is organized to suit these functions, and causal knowledge describes how these arrangements work. We have been exploring the hypothesis that vision is an explanatory process in which causal and functional reasoning plays an intimate role in mediating the activity of low-level visual processes. In particular, we have explored two of the consequences of this view for the construction of purposeful vision systems: Causal and design knowledge can be used to 1) drive focus of attention, and 2) choose between ambiguous image interpretations. Both principles are at work in SPROCKET, a system which visually explores simple machines, integrating diverse visual clues into an explanation of a machine's design and function.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
PublisherPubl by AAAI
Pages588-593
Number of pages6
ISBN (Print)0262510715
StatePublished - Dec 1 1993
EventProceedings of the 11th National Conference on Artificial Intelligence - Washington, DC, USA
Duration: Jul 11 1993Jul 15 1993

Other

OtherProceedings of the 11th National Conference on Artificial Intelligence
CityWashington, DC, USA
Period7/11/937/15/93

Fingerprint

Machine design

ASJC Scopus subject areas

  • Software

Cite this

Brand, M., Birnbaum, L. A., & Cooper, P. (1993). Sensible scenes: visual understanding of complex structures through causal analysis. In Proceedings of the National Conference on Artificial Intelligence (pp. 588-593). Publ by AAAI.
Brand, Matthew ; Birnbaum, Lawrence A ; Cooper, Paul. / Sensible scenes : visual understanding of complex structures through causal analysis. Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, 1993. pp. 588-593
@inproceedings{479f05eb99b347aeb73b2cc644106d80,
title = "Sensible scenes: visual understanding of complex structures through causal analysis",
abstract = "An important result of visual understanding is an explanation of a scene's causal structure: How action - usually motion - is originated, constrained, and prevented, and how this determines what will happen in the immediate future. To be useful for a purposeful agent, these explanations must also capture the scene in terms of the functional properties of its objects - their purposes, uses, and affordances for manipulation. Design knowledge describes how the world is organized to suit these functions, and causal knowledge describes how these arrangements work. We have been exploring the hypothesis that vision is an explanatory process in which causal and functional reasoning plays an intimate role in mediating the activity of low-level visual processes. In particular, we have explored two of the consequences of this view for the construction of purposeful vision systems: Causal and design knowledge can be used to 1) drive focus of attention, and 2) choose between ambiguous image interpretations. Both principles are at work in SPROCKET, a system which visually explores simple machines, integrating diverse visual clues into an explanation of a machine's design and function.",
author = "Matthew Brand and Birnbaum, {Lawrence A} and Paul Cooper",
year = "1993",
month = "12",
day = "1",
language = "English (US)",
isbn = "0262510715",
pages = "588--593",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "Publ by AAAI",

}

Brand, M, Birnbaum, LA & Cooper, P 1993, Sensible scenes: visual understanding of complex structures through causal analysis. in Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, pp. 588-593, Proceedings of the 11th National Conference on Artificial Intelligence, Washington, DC, USA, 7/11/93.

Sensible scenes : visual understanding of complex structures through causal analysis. / Brand, Matthew; Birnbaum, Lawrence A; Cooper, Paul.

Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, 1993. p. 588-593.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Sensible scenes

T2 - visual understanding of complex structures through causal analysis

AU - Brand, Matthew

AU - Birnbaum, Lawrence A

AU - Cooper, Paul

PY - 1993/12/1

Y1 - 1993/12/1

N2 - An important result of visual understanding is an explanation of a scene's causal structure: How action - usually motion - is originated, constrained, and prevented, and how this determines what will happen in the immediate future. To be useful for a purposeful agent, these explanations must also capture the scene in terms of the functional properties of its objects - their purposes, uses, and affordances for manipulation. Design knowledge describes how the world is organized to suit these functions, and causal knowledge describes how these arrangements work. We have been exploring the hypothesis that vision is an explanatory process in which causal and functional reasoning plays an intimate role in mediating the activity of low-level visual processes. In particular, we have explored two of the consequences of this view for the construction of purposeful vision systems: Causal and design knowledge can be used to 1) drive focus of attention, and 2) choose between ambiguous image interpretations. Both principles are at work in SPROCKET, a system which visually explores simple machines, integrating diverse visual clues into an explanation of a machine's design and function.

AB - An important result of visual understanding is an explanation of a scene's causal structure: How action - usually motion - is originated, constrained, and prevented, and how this determines what will happen in the immediate future. To be useful for a purposeful agent, these explanations must also capture the scene in terms of the functional properties of its objects - their purposes, uses, and affordances for manipulation. Design knowledge describes how the world is organized to suit these functions, and causal knowledge describes how these arrangements work. We have been exploring the hypothesis that vision is an explanatory process in which causal and functional reasoning plays an intimate role in mediating the activity of low-level visual processes. In particular, we have explored two of the consequences of this view for the construction of purposeful vision systems: Causal and design knowledge can be used to 1) drive focus of attention, and 2) choose between ambiguous image interpretations. Both principles are at work in SPROCKET, a system which visually explores simple machines, integrating diverse visual clues into an explanation of a machine's design and function.

UR - http://www.scopus.com/inward/record.url?scp=0027704771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027704771&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0262510715

SP - 588

EP - 593

BT - Proceedings of the National Conference on Artificial Intelligence

PB - Publ by AAAI

ER -

Brand M, Birnbaum LA, Cooper P. Sensible scenes: visual understanding of complex structures through causal analysis. In Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI. 1993. p. 588-593